Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructiveHint=true, and the description reinforces it with the key behavioral fact the annotation cannot convey: Gmail replaces the whole draft and there is no partial edit. It also adds permission requirements (gmail.compose), a reconnect hint for older accounts, and the no-send guarantee – all beyond structured data. It leaves some ambiguity about whether omitting optional cc/thread_id clears those values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The paragraph is front-loaded with the core replacement semantics, then layers the send/no-send and permission context efficiently. Sentence density is high with em-dash asides, but every clause carries distinct information and none is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation with no output schema, the description covers the essentials an agent needs: replacement (not merge) semantics, the no-send guarantee, required permissions, reconnect behavior, and account disambiguation. The only gap is the effect of omitting optional fields like cc or thread_id, which matters for a whole-message replacement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 7 parameters, setting the baseline at 3. The description reinforces required-field parity with create_draft and repeats the multi-account condition for `account`, but adds no new syntax or format detail beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Replace an existing Gmail draft's content') and immediately distinguishes it from siblings, noting it takes the same required fields as create_draft and that nothing is sent (unlike send_draft). An agent can tell what this does and how it differs from related draft tools without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear when-to-use context by framing this as the replace path for an existing draft versus create_draft, and clarifies the send step routes through Gmail or send_draft. It also supplies the account-selection condition ('Pass account when more than one Gmail account is connected'). It stops short of explicit when-not guidance but the replacement framing is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.